@strickvl

4 Followers
3 Following
279 Posts
Machine Learning Engineer, researcher (& author of a few books in my old life as a historian).
Love learning languages (machine and human), cats and sharks. Studying Mathematics @ the Open University. Budding J enthusiast.
linkedinhttps://linkedin.com/in/strickvl
githubhttps://github.com/strickvl
bloghttps://mlops.systems/
strickvl6d ago

Just made a bumper release this evening: 25 new format adapters covering the major cloud annotation platforms, autonomous-driving and aerial datasets, document layout, synthetic data, and the long tail of academic/community formats. Panlabel now reads and writes 40+ object detection annotation formats, which I think covers almost all the options!

I think I'll move onto a new domain / format now. Either segmentation or maybe I'll dip my toes into text datasets / formats!
https://github.com/strickvl/panlabel/releases/tag/v0.7.0

Show threadstrickvlApr 13
Repo: https://github.com/zenml-io/kitaru
GitHub - zenml-io/kitaru: Durable execution for AI agents, built on ZenML

Durable execution for AI agents, built on ZenML. Contribute to zenml-io/kitaru development by creating an account on GitHub.

GitHub
Show threadstrickvlApr 13
We considered integrating with Mem0, Letta and the other dedicated memory providers. We learned a lot from reading their code and their philosophies, there's real diversity in how this space thinks about the problem. But once we mapped out what versioning and provenance would look like across two systems, the seams started showing. Sarah Wooders' framing (which Harrison also quotes) captures why: managing memory is a core responsibility of the harness, not a peripheral one.
Show threadstrickvlApr 13
3. Provenance is automatic. Because memory and artifacts share a backend, you don't have to stitch the audit trail back together across systems. (And we offer a full audit log in case you need that for your memories.)
Show threadstrickvlApr 13
2. Scopes match how agents actually work. Namespace for repo conventions, flow for per-agent learned state, execution for per-run progress. No cramming everything into one global blob.
Show threadstrickvlApr 13

Three things fell out of putting memory in the same substrate that already handles execution durability:

1. Versioning comes free. Every memory.set() creates a new version. Soft deletes leave tombstones. You can ask "which run taught the agent this?" and get an actual answer. (And since memory ships through our MCP server, you can ask Claude Code or Codex that question directly.)

strickvlApr 13

"Your Harness, Your Memory" by Harrison Chase argues that memory belongs inside your agent harness, not behind a third-party API. We've been building exactly that, and Kitaru 0.4.0 shipped it this morning.

https://kitaru.ai/blog/kitaru-agents-now-have-memory/

Kitaru agents now have memory — Kitaru Blog

Durable, versioned memory for agents is now built into Kitaru — across Python, the typed client, the CLI, and MCP.

Show threadstrickvlApr 8

Each platform has its own migration story. Dagster's asset-first world needs different thinking than Airflow's scheduler-first model.

For cloud platforms (AzureML, SageMaker, Vertex AI), the skills support "keep the backend" paths.

Works with Claude Code, Cursor, Codex, or any coding agent. Open-source and free. Feedback very welcome!

https://github.com/zenml-io/skills

GitHub - zenml-io/skills: AI coding agent skills for ZenML MLOps workflows — quick wins, pipeline setup, and more

AI coding agent skills for ZenML MLOps workflows — quick wins, pipeline setup, and more - zenml-io/skills

GitHub
strickvlApr 8

We just shipped migration skills that help you try out ZenML from 11 ML/data platforms: Airflow, Argo, AzureML, Dagster, Databricks, Flyte, Kedro, Metaflow, Prefect, SageMaker, Vertex AI.

Each skill has hand-curated concept maps showing what maps 1:1, what's approximate, and what needs redesign. Plus ZenML best practices baked in and a conservative approach that flags uncertainty rather than guessing.

#MLOps #AgenticCoding #MachineLearning #OpenSource

Show threadstrickvlMar 15

That brings panlabel to 13 supported formats with full read, write, and auto-detection. Single binary, no Python dependencies.

This is the kind of project I enjoy just steadily plodding away at — ticking off one format at a time until every common object detection annotation format is covered.

https://github.com/strickvl/panlabel

#ObjectDetection #Rust #MachineLearning #ComputerVision #OpenSource

GitHub - strickvl/panlabel: Universal annotation converter

Universal annotation converter. Contribute to strickvl/panlabel development by creating an account on GitHub.

GitHub